Machine-learned pharmacology optimization

A method for optimizing pharmacological compound development, comprising:

• a. accessing, for each compound of a plurality of compounds, effect information describing an effect of the compound;
• b. iteratively training a machine-learned compound experiment model until a threshold criterion is satisfied by:
• i. generating, for each of a plurality of experiments, a corresponding set of compounds to combine together in the experiment using the effect information;
• ii. performing, for each of the plurality of experiments, the experiment by applying the corresponding set of compounds in a subject;
• iii. determining, for each of the plurality of experiments, a resulting set of effects of the applied set of compounds within the subject;
• iv. determining, for each of the plurality of experiments, an association between each effect of the resulting set of effects and a compound of the applied set of compounds to which the effect is attributed;
• and
• v. updating the effect information based on the determined associations between effects and compounds;
• vi. wherein the total number of experiments performed while training the compound experiment model is less than a total number of possible combinations of the plurality of compounds.